从UNI2-h到ConvNeXt-T：基于知识蒸馏的轻量级细胞核实例分割
From UNI2-h to ConvNeXt-T: Lightweight Nuclei Instance Segmentation via Knowledge Distillation
浏览论文内容
中文总结 AI 辅助
针对高精度细胞核分割模型推理慢的问题，提出将UNI2-h蒸馏至ConvNeXt-Tiny学生网络，仅用1/20参数达到教师98.8%的mPQ，并实现21.8倍加速。
中文摘要 AI 辅助
细胞核实例分割是数字病理学的核心任务，然而高精度模型依赖大型视觉Transformer（ViT）编码器，其推理速度无法满足实时临床需求。我们提出了一种轻量级方案，通过输出级知识蒸馏，将UNI2-h病理基础模型蒸馏到ConvNeXt-Tiny学生网络（Ours-T，34.7M参数，为教师网络的1/20）。Ours-T在PanNuke上达到0.519的mPQ（为教师网络的98.8%），在MoNuSeg上达到0.668的零样本bPQ，推理速度为634.3张/秒，仅需0.045秒即可完成全分辨率1024^2图像分析（加速21.8倍）。实验进一步表明，多尺度门控卷积（MALA）在ViT编码器下无增益，仅输出级蒸馏即可实现高效知识迁移。
英文摘要
Nuclei instance segmentation is a core task in digital pathology, yet high-accuracy models rely on large vision transformer (ViT) encoders whose inference speed cannot meet real-time clinical demands. We propose a lightweight scheme that distills the UNI2-h pathology foundation model into a ConvNeXt-Tiny student (Ours-T, 34.7M parameters, 1/20 of the teacher) via output-level knowledge distillation. Ours-T achieves an mPQ of 0.519 on PanNuke (98.8% of the teacher), a zero-shot bPQ of 0.668 on MoNuSeg, and an inference speed of 634.3 img/s, requiring only 0.045 s for full-resolution 1024^2 analysis (21.8x speedup). Experiments further show that multi-scale gated convolution (MALA) yields no gain under ViT encoders, and output-level distillation alone suffices for efficient knowledge transfer.
发表机构
- School of Computer Science, Wuhan University（武汉大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。
